feat(context): enhance performance, caching, and settings management

- Replace hard-coded limits with configurable settings (e.g., cache memory size, truncation strategy, relevance settings).
- Optimize parallel execution in token counting, scoring, and reranking for source diversity.
- Improve caching logic:
  - Add per-context locks for safe parallel scoring.
  - Reuse precomputed fingerprints for cache efficiency.
- Make truncation, scoring, and ranker behaviors fully configurable via settings.
- Add support for middle truncation, context hash-based hashing, and dynamic token limiting.
- Refactor methods for scalability and better error handling.

Tests: Updated all affected components with additional test cases.

backend/app/services/context/cache/context_cache.py

@@ -54,7 +54,7 @@ class ContextCache:
 
         # In-memory fallback cache when Redis unavailable
         self._memory_cache: dict[str, tuple[str, float]] = {}
-        self._max_memory_items = 1000
+        self._max_memory_items = self._settings.cache_memory_max_items
 
     def set_redis(self, redis: "Redis") -> None:
         """Set Redis connection."""
@@ -100,7 +100,7 @@ class ContextCache:
         Compute a fingerprint for a context assembly request.
 
         The fingerprint is based on:
-        - Context content and metadata
+        - Context content hash and metadata (not full content for performance)
         - Query string
         - Target model
 
@@ -112,12 +112,13 @@ class ContextCache:
         Returns:
             32-character hex fingerprint
         """
-        # Build a deterministic representation
+        # Build a deterministic representation using content hashes for performance
+        # This avoids JSON serializing potentially large content strings
         context_data = []
         for ctx in contexts:
             context_data.append({
                 "type": ctx.get_type().value,
-                "content": ctx.content,
+                "content_hash": self._hash_content(ctx.content),  # Hash instead of full content
                 "source": ctx.source,
                 "priority": ctx.priority,  # Already an int
             })